diff --git a/AGENTS.md b/AGENTS.md index a06694fe..7d4ab6d1 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -73,6 +73,7 @@ Clean test-only scratch directories after verification with `find tests -maxdept - `scripts/import_telemetry_events.py`: external telemetry importer. Validate the whole input before appending events, and keep raw prompt/output/transcript/message/note fields blocked. - `scripts/emit_telemetry_event.py`: external client telemetry emitter. It may append one normalized metadata event to a local spool, but must never accept or write raw prompt, output, transcript, message, note, argument, or private content. - `scripts/render_telemetry_hook_recipes.py`: client hook recipe report. Keep recipes metadata-only, mark native auto-capture as unclaimed unless a real client integration exists, and preserve dry-run commands for Browser/Chrome/IDE/wrapper adapters. +- `scripts/telemetry_native_host.py`: Browser/Chrome Native Messaging telemetry bridge. Preserve length-prefixed stdio behavior, raw-content blocking, and launcher/manifest generation tests. New helper modules that are imported by CLI/report scripts but are not standalone commands must declare: diff --git a/Makefile b/Makefile index 0b1e155f..ca2ef648 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ PYTHON ?= python3 LOCAL_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills.disabled/yao-meta-skill ACTIVE_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills/yao-meta-skill -.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean +.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean eval: $(PYTHON) scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt @@ -100,6 +100,9 @@ telemetry-emit-check: telemetry-hooks-check: $(PYTHON) tests/verify_telemetry_hooks.py +telemetry-native-host-check: + $(PYTHON) tests/verify_telemetry_native_host.py + review-waivers-check: $(PYTHON) tests/verify_review_waivers.py @@ -196,11 +199,11 @@ sync-local-install: package-check sync-active-install: package-check $(PYTHON) scripts/sync_local_install.py --install-dir "$(ACTIVE_SKILL_INSTALL_DIR)" -test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check +test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check ci-test: $(PYTHON) scripts/ci_test.py clean: - rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_skill_overview tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_feedback tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md + rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_skill_overview tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_feedback tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_telemetry_native_host tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md find . -type d -name __pycache__ -prune -exec rm -rf {} + diff --git a/README.md b/README.md index 640e0cd0..321775eb 100644 --- a/README.md +++ b/README.md @@ -32,6 +32,7 @@ It turns rough workflows, transcripts, prompts, notes, and runbooks into reusabl - three high-value next iteration directions after the first package is created - a lightweight feedback log that does not require a full promotion cycle - a local-first metadata-only adoption and drift report that turns real usage signals into next iteration candidates, with optional `yao.py` CLI run capture, external client event emit hooks, hook recipes, and JSONL import that record command names and outcomes without arguments or raw content +- a Browser/Chrome Native Messaging telemetry host that can receive length-prefixed metadata-only client events and generate a local launcher plus manifest without storing raw content - a Skill Atlas drift layer that reads aggregate adoption reports and surfaces portfolio-level drift signals without packaging raw telemetry logs - a baseline compare report for with-skill vs baseline review - a conversation-style, archetype-aware quickstart that steers new packages toward scaffold, production, library, or governed fits @@ -111,6 +112,7 @@ python3 scripts/yao.py adoption-drift my-skill --record-event skill_activation - YAO_CLI_TELEMETRY=1 python3 scripts/yao.py validate my-skill python3 scripts/yao.py telemetry-emit my-skill --event skill_activation --activation-type explicit --outcome accepted --command browser-extension python3 scripts/yao.py telemetry-hooks my-skill +python3 scripts/telemetry_native_host.py my-skill --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/ python3 scripts/yao.py telemetry-import my-skill --input-jsonl /tmp/external-client-events.jsonl --command browser-extension python3 scripts/yao.py review-waivers my-skill --add-waiver --gate-key trust-report --reviewer "Yao Team" --reason "Known warning accepted for this release with bounded follow-up." --expires-at 2026-09-30 python3 scripts/yao.py review-waivers my-skill --add-waiver --gate-key permission-gates --reviewer "Yao Team" --reason "Permission warning accepted only for this non-governed release window." --expires-at 2026-09-30 @@ -420,6 +422,7 @@ Utility scripts that make the meta-skill operational: - `import_telemetry_events.py`: imports external metadata-only telemetry JSONL after whole-file privacy validation, then refreshes the aggregate adoption drift report - `emit_telemetry_event.py`: emits one metadata-only external client event into a local spool for later `telemetry-import`, with dry-run validation and raw-content field blocking - `render_telemetry_hook_recipes.py`: renders Browser, Chrome, VS Code, CLI wrapper, and provider-adapter telemetry hook recipes with dry-run commands and explicit native-integration caveats +- `telemetry_native_host.py`: receives Browser/Chrome Native Messaging length-prefixed JSON events, rejects raw-content fields, appends metadata-only events, and writes local launcher/manifest files for operator installation - `yao_cli_telemetry.py`: opt-in metadata-only `yao.py` run capture for command name, source, outcome, and failure class without command arguments or raw content - `render_review_waivers.py`: validates human reviewer risk approvals with gate keys, reasons, expiry dates, and blocker-safe waiver policy - `init_skill.py`, `lint_skill.py`, `validate_skill.py`, `diff_eval.py`: minimal authoring toolchain diff --git a/references/telemetry-drift-method.md b/references/telemetry-drift-method.md index 0f20480f..32e1bf1d 100644 --- a/references/telemetry-drift-method.md +++ b/references/telemetry-drift-method.md @@ -107,6 +107,28 @@ The report is written to: Each recipe includes a dry-run command, an emit command, the target local spool, trigger points, and the privacy contract. The report intentionally sets `native_auto_capture=false`; it proves the local hook contract and metadata-only command shape, not that a host client is already natively integrated. +## Browser Native Host + +`scripts/telemetry_native_host.py` implements the local side of Browser/Chrome Native Messaging. It accepts length-prefixed JSON messages on stdio, validates them with the same metadata-only telemetry contract, appends accepted events to the local spool, and rejects raw prompt/output/transcript/message/note fields. + +Smoke-test one message without Browser installation: + +```bash +python3 scripts/telemetry_native_host.py . \ + --message-json '{"event":"skill_activation","activation_type":"explicit","outcome":"accepted","failure_type":"none","command":"chrome-native-host"}' +``` + +Generate a local launcher and Chrome native messaging manifest for an operator-installed extension: + +```bash +python3 scripts/telemetry_native_host.py . \ + --write-launcher /tmp/yao-telemetry-host.sh \ + --write-manifest /tmp/yao-telemetry-host.json \ + --allowed-origin chrome-extension://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/ +``` + +This is an executable native host bridge and manifest generator. It still does not prove that a specific Browser/Chrome extension is installed or sending events in the user's environment. + ## External Client Import External clients, browser extensions, editor adapters, or wrapper scripts may hand off already-sanitized JSONL through `telemetry-import`: diff --git a/registry/index.json b/registry/index.json index 8e951a6b..6954dde7 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 701e7651..0e899444 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339", - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index b6b888bc..8b5423d1 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -209,6 +209,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -270,7 +271,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -376,7 +377,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -425,6 +426,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -464,14 +466,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -493,7 +495,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -514,7 +516,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -525,7 +527,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -606,7 +608,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -655,6 +657,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -694,14 +697,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -721,7 +724,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -742,7 +745,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -753,7 +756,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -1019,6 +1022,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -1080,7 +1084,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -1186,7 +1190,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1235,6 +1239,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -1274,14 +1279,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1303,7 +1308,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -1324,7 +1329,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -1335,7 +1340,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -1416,7 +1421,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1465,6 +1470,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -1504,14 +1510,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1531,7 +1537,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -1552,7 +1558,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -1563,7 +1569,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -1829,6 +1835,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -1890,7 +1897,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -1996,7 +2003,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2045,6 +2052,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -2084,14 +2092,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2113,7 +2121,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -2134,7 +2142,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -2144,7 +2152,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -2219,7 +2227,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2268,6 +2276,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -2307,14 +2316,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2334,7 +2343,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -2355,7 +2364,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -2365,7 +2374,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -2623,6 +2632,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -2684,7 +2694,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -2790,7 +2800,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2839,6 +2849,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -2878,14 +2889,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2907,7 +2918,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -2928,7 +2939,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -2939,7 +2950,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -3013,7 +3024,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3062,6 +3073,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -3101,14 +3113,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3128,7 +3140,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -3149,7 +3161,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -3160,7 +3172,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -3417,6 +3429,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -3478,7 +3491,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -3584,7 +3597,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3633,6 +3646,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -3672,14 +3686,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3701,7 +3715,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -3722,7 +3736,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -3733,7 +3747,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -3811,7 +3825,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3860,6 +3874,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -3899,14 +3914,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3926,7 +3941,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -3947,7 +3962,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -3958,7 +3973,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { diff --git a/reports/context_budget.json b/reports/context_budget.json index 541568a5..59344ffa 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,10 +6,10 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 936263, + "other_text_tokens": 941577, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 937014, - "relevant_file_count": 409, + "estimated_total_text_tokens": 942328, + "relevant_file_count": 413, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 137.7 diff --git a/reports/install_simulation.json b/reports/install_simulation.json index 801b752a..cdcb767a 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -8,7 +8,7 @@ "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 503, + "archive_entry_count": 505, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 300044e1..70876b31 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.49, + "duration_ms": 31.95, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.15, + "duration_ms": 34.87, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.31, + "duration_ms": 33.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.67, + "duration_ms": 48.91, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.54, + "duration_ms": 34.71, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.43, + "duration_ms": 33.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.8, + "duration_ms": 34.16, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.96, + "duration_ms": 32.68, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.79, + "duration_ms": 29.95, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.95, + "duration_ms": 28.78, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index c42bcfae..2a5b073e 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 34.49 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 33.15 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 34.31 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 30.67 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 29.54 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.43 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.8 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.96 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.79 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.95 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 31.95 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 34.87 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 33.23 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 48.91 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 34.71 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 33.42 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 34.16 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 32.68 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 29.95 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.78 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 76b7f86f..17fd2ac9 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,8 +8,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", - "archive_entry_count": 503, + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", + "archive_entry_count": 505, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index 298e422d..49808af0 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf` +- Archive SHA256: `7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 9037247d..2f312c57 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339", - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index ce16199f..735230bc 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339` -- Archive SHA256: `15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf` +- Package SHA256: `e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc` +- Archive SHA256: `7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 96d4264a..60bead5e 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -242,12 +242,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review A/B0/5

adjudication decisions; pending 5

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native enforcement targets

Trust0

73 scripts scanned; secrets found

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

503 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review A/B0/5

adjudication decisions; pending 5

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native enforcement targets

Trust0

74 scripts scanned; secrets found

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

505 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 944/1000; quality density 137.7

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 73 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 944/1000; quality density 137.7

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 74 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

@@ -313,7 +313,7 @@
-

信任报告

Secret
0
脚本数
73
网络脚本
3
Help 失败
0
包体哈希
25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339
+

信任报告

Secret
0
脚本数
74
网络脚本
3
Help 失败
0
包体哈希
e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

@@ -344,12 +344,12 @@

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
503
失败数
0
警告数
0
归档哈希
15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
505
失败数
0
警告数
0
归档哈希
7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3
diff --git a/reports/review-studio.json b/reports/review-studio.json index bcf9a5b6..809f72bc 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -59,7 +59,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 73 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 74 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -355,7 +355,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 350 个词/字，references 约 15206 个词/字。", + "入口约 350 个词/字，references 约 15316 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -459,7 +459,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 350 个词/字，references 约 15206 个词/字。" + "上下文成本需要补强：入口约 350 个词/字，references 约 15316 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -692,7 +692,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 73 + "file_count": 74 }, { "path": "evals", @@ -707,7 +707,7 @@ "file_count": 173 } ], - "file_count": 310, + "file_count": 311, "folder_count": 4, "distribution": [ { @@ -732,7 +732,7 @@ }, { "label": "scripts", - "value": 73 + "value": 74 }, { "label": "evals", @@ -861,7 +861,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 73 + "file_count": 74 }, { "path": "evals", @@ -1207,8 +1207,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 157, - "script_count": 73, + "scanned_files": 158, + "script_count": 74, "internal_module_count": 10, "secret_findings": 0, "dependency_files": [ @@ -1217,18 +1217,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 50, + "file_write_script_count": 51, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 63, + "help_smoke_checked_count": 64, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 157, - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_hash_file_count": 158, + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" }, "skill_atlas": { "skill_count": 12, @@ -1266,8 +1266,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339", - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, "compatibility": { "openai": "pass", @@ -1298,7 +1298,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1314,8 +1314,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", - "archive_entry_count": 503, + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", + "archive_entry_count": 505, "failure_count": 0, "warning_count": 0 }, @@ -1326,7 +1326,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 503, + "archive_entry_count": 505, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1393,12 +1393,12 @@ { "field": "archive_sha256", "from": "", - "to": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "to": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "to": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, @@ -3132,7 +3132,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.49, + "duration_ms": 31.95, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3160,7 +3160,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.15, + "duration_ms": 34.87, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3183,7 +3183,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.31, + "duration_ms": 33.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3211,7 +3211,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.67, + "duration_ms": 48.91, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3234,7 +3234,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.54, + "duration_ms": 34.71, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3262,7 +3262,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.43, + "duration_ms": 33.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3285,7 +3285,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.8, + "duration_ms": 34.16, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3312,7 +3312,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.96, + "duration_ms": 32.68, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3335,7 +3335,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.79, + "duration_ms": 29.95, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3364,7 +3364,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.95, + "duration_ms": 28.78, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3882,6 +3882,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -3943,7 +3944,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -4049,7 +4050,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -4098,6 +4099,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -4137,14 +4139,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4166,7 +4168,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -4187,7 +4189,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -4198,7 +4200,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -4279,7 +4281,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -4328,6 +4330,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -4367,14 +4370,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4394,7 +4397,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -4415,7 +4418,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -4426,7 +4429,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -4692,6 +4695,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -4753,7 +4757,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -4859,7 +4863,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -4908,6 +4912,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -4947,14 +4952,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4976,7 +4981,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -4997,7 +5002,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -5008,7 +5013,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -5089,7 +5094,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -5138,6 +5143,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -5177,14 +5183,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -5204,7 +5210,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -5225,7 +5231,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -5236,7 +5242,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -5502,6 +5508,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -5563,7 +5570,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -5669,7 +5676,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -5718,6 +5725,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -5757,14 +5765,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -5786,7 +5794,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -5807,7 +5815,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -5817,7 +5825,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -5892,7 +5900,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -5941,6 +5949,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -5980,14 +5989,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -6007,7 +6016,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -6028,7 +6037,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -6038,7 +6047,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -6296,6 +6305,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -6357,7 +6367,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -6463,7 +6473,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -6512,6 +6522,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -6551,14 +6562,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -6580,7 +6591,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -6601,7 +6612,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -6612,7 +6623,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -6686,7 +6697,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -6735,6 +6746,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -6774,14 +6786,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -6801,7 +6813,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -6822,7 +6834,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -6833,7 +6845,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -7090,6 +7102,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -7151,7 +7164,7 @@ ], "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 } @@ -7257,7 +7270,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -7306,6 +7319,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -7345,14 +7359,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -7374,7 +7388,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -7395,7 +7409,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -7406,7 +7420,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -7484,7 +7498,7 @@ }, "file_write": { "required": true, - "script_count": 50, + "script_count": 51, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -7533,6 +7547,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -7572,14 +7587,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 63, + "checked_count": 64, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 50, + "file_write_script_count": 51, "subprocess_script_count": 7, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -7599,7 +7614,7 @@ ], "capability_counts": { "network": 3, - "file_write": 50, + "file_write": 51, "subprocess": 7, "interactive": 0 }, @@ -7620,7 +7635,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 32, - "scripts": 73, + "scripts": 74, "assets": 2, "reports": 43 }, @@ -7631,7 +7646,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 73, + "script_count": 74, "help_smoke_failed_count": 0 }, "permissions": { @@ -8271,8 +8286,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 157, - "script_count": 73, + "scanned_files": 158, + "script_count": 74, "internal_module_count": 10, "secret_findings": 0, "dependency_files": [ @@ -8281,18 +8296,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 50, + "file_write_script_count": 51, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 63, + "help_smoke_checked_count": 64, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 157, - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_hash_file_count": 158, + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" }, "failures": [], "warnings": [], @@ -9211,6 +9226,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/telemetry_native_host.py", + "interface": "cli", + "interface_declared": false, + "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/trigger_eval.py", "interface": "cli", @@ -9368,9 +9397,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 63, - "checked_count": 63, - "passed_count": 63, + "candidate_count": 64, + "checked_count": 64, + "passed_count": 64, "failed_count": 0, "skipped_count": 10, "failed_scripts": [], @@ -9945,6 +9974,16 @@ "stdout_excerpt": "usage: sync_local_install.py [-h] [--root ROOT] [--install-dir INSTALL_DIR]\n [--package-dir PACKAGE_DIR]\n [--generated-at GENERATED_AT]\n [--skip-install-pre", "stderr_excerpt": "" }, + { + "path": "scripts/telemetry_native_host.py", + "command": "python3 scripts/telemetry_native_host.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: telemetry_native_host.py [-h] [--output-jsonl OUTPUT_JSONL]\n [--message-json MESSAGE_JSON] [--stdio]\n [--dry-run] [--write-manifest WRITE_MANIFEST]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/trigger_eval.py", "command": "python3 scripts/trigger_eval.py --help", @@ -10148,6 +10187,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" @@ -10217,10 +10257,10 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 936263, + "other_text_tokens": 941577, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 937014, - "relevant_file_count": 409, + "estimated_total_text_tokens": 942328, + "relevant_file_count": 413, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 137.7 @@ -11148,6 +11188,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", @@ -12220,8 +12261,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339", - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, "compatibility": { "openai": "pass", @@ -12252,7 +12293,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -12277,7 +12318,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, @@ -12300,8 +12341,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", - "archive_entry_count": 503, + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", + "archive_entry_count": 505, "failure_count": 0, "warning_count": 0 }, @@ -12966,7 +13007,7 @@ "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 503, + "archive_entry_count": 505, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -13308,12 +13349,12 @@ { "field": "archive_sha256", "from": "", - "to": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "to": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "to": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 6b65e85d..d5a2bc8c 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,8 +2,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 157, - "script_count": 73, + "scanned_files": 158, + "script_count": 74, "internal_module_count": 10, "secret_findings": 0, "dependency_files": [ @@ -12,18 +12,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 50, + "file_write_script_count": 51, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 63, + "help_smoke_checked_count": 64, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 157, - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_hash_file_count": 158, + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" }, "failures": [], "warnings": [], @@ -942,6 +942,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/telemetry_native_host.py", + "interface": "cli", + "interface_declared": false, + "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/trigger_eval.py", "interface": "cli", @@ -1099,9 +1113,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 63, - "checked_count": 63, - "passed_count": 63, + "candidate_count": 64, + "checked_count": 64, + "passed_count": 64, "failed_count": 0, "skipped_count": 10, "failed_scripts": [], @@ -1676,6 +1690,16 @@ "stdout_excerpt": "usage: sync_local_install.py [-h] [--root ROOT] [--install-dir INSTALL_DIR]\n [--package-dir PACKAGE_DIR]\n [--generated-at GENERATED_AT]\n [--skip-install-pre", "stderr_excerpt": "" }, + { + "path": "scripts/telemetry_native_host.py", + "command": "python3 scripts/telemetry_native_host.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: telemetry_native_host.py [-h] [--output-jsonl OUTPUT_JSONL]\n [--message-json MESSAGE_JSON] [--stdio]\n [--dry-run] [--write-manifest WRITE_MANIFEST]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/trigger_eval.py", "command": "python3 scripts/trigger_eval.py --help", @@ -1879,6 +1903,7 @@ "scripts/run_output_execution.py", "scripts/simulate_install.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trust_check.py", "scripts/upgrade_check.py", "scripts/verify_package.py" diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index f7cba361..8337dadc 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,22 +1,22 @@ # Security Trust Report - OK: `True` -- Scanned files: `157` -- Scripts: `73` +- Scanned files: `158` +- Scripts: `74` - Internal script modules: `10` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` - Network policy missing scripts: `0` -- File-write scripts: `50` +- File-write scripts: `51` - Permission approvals: `3 / 3` - Permission approval gaps: `0` -- CLI help smoke checked: `63` +- CLI help smoke checked: `64` - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `157` -- Package SHA256: `25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339` +- Package hash files: `158` +- Package SHA256: `e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc` ## Failures @@ -54,8 +54,8 @@ - Enabled: `True` - Timeout seconds: `5.0` -- Checked scripts: `63` -- Passed scripts: `63` +- Checked scripts: `64` +- Passed scripts: `64` - Failed scripts: `none` ## Script Surface @@ -126,6 +126,7 @@ | scripts/skill_report_metrics.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to calculate overview report metrics. | | scripts/skill_report_model.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to build the v2 report data model. | | scripts/sync_local_install.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | +| scripts/telemetry_native_host.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/trigger_eval.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/trust_check.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/upgrade_check.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index 3ac584c5..41f89e33 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -26,6 +26,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree - External Telemetry Import v0 for whole-file validated metadata-only JSONL ingestion from non-CLI clients, with dry-run support and all-or-nothing rejection on raw content fields or schema violations. - Telemetry Emit Hook v0 for Browser/Chrome/IDE/wrapper integrations to append one validated metadata-only external event into a local spool before import, with dry-run validation and raw-content blocking. - Telemetry Hook Recipes v0 for Browser, Chrome, VS Code, CLI wrapper, and provider-adapter recipe generation with dry-run commands, metadata-only privacy checks, and explicit non-claiming of native host integration. +- Telemetry Native Host v0 for Browser/Chrome Native Messaging length-prefixed stdio, metadata-only event validation, local launcher generation, and Chrome host manifest generation. - Review Waivers v0 for human warning acceptance with reviewer, reason, scope, expiry, and blocker-safe policy. - Governed Permission Gates v0 for reviewer-approved network, file-write, and subprocess capabilities with scope, reason, expiry, evidence, and target-enforcement mapping. - Runtime Permission Probes v0 for packaged target adapter checks, explicit native-enforcement flags, metadata fallback evidence, and residual permission risks. @@ -37,7 +38,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree - Output Review Adjudication now preserves blind-review integrity by hiding expected winners for pending or invalid reviewer decisions; answer keys are revealed only after a valid A/B decision exists for that case. - Provider Output Eval Runner v0 so `python3 scripts/yao.py output-exec --provider-runner openai` can collect real provider-backed model evidence through a reviewed OpenAI Responses API compatible runner instead of ad hoc shell glue. -This is still not the final world-class state. Target-native behavior contracts are now explicit, VS Code / Copilot package metadata is auditable, local output-eval command execution is wired, blind-review answers remain hidden until valid decisions exist, a provider-backed output runner exists, installer-level permission coverage is now locally enforced during install simulation and local install sync, opt-in `yao.py` CLI telemetry can capture metadata-only real run signals, external clients can now emit one validated metadata-only event into a local spool, hook recipes now make Browser/Chrome/VS Code/wrapper/provider-adapter integration commands auditable, validated external JSONL imports can bring those non-CLI client signals into the same drift loop, and Skill Atlas now consumes aggregate drift reports. Review Studio keeps pending human adjudication visible as a warning instead of treating it as a clean pass. Deeper provider-native execution transforms, platform-native automatic client telemetry implementations, provider-native installer integration, real provider holdout runs, real human adjudication decisions, and native runtime permission enforcement remain open. +This is still not the final world-class state. Target-native behavior contracts are now explicit, VS Code / Copilot package metadata is auditable, local output-eval command execution is wired, blind-review answers remain hidden until valid decisions exist, a provider-backed output runner exists, installer-level permission coverage is now locally enforced during install simulation and local install sync, opt-in `yao.py` CLI telemetry can capture metadata-only real run signals, external clients can now emit one validated metadata-only event into a local spool, hook recipes now make Browser/Chrome/VS Code/wrapper/provider-adapter integration commands auditable, a Browser/Chrome Native Messaging host can receive length-prefixed metadata events and generate a local launcher plus manifest, validated external JSONL imports can bring those non-CLI client signals into the same drift loop, and Skill Atlas now consumes aggregate drift reports. Review Studio keeps pending human adjudication visible as a warning instead of treating it as a clean pass. Deeper provider-native execution transforms, installed platform-native client telemetry implementations, provider-native installer integration, real provider holdout runs, real human adjudication decisions, and native runtime permission enforcement remain open. ## Coverage Matrix @@ -58,7 +59,7 @@ This is still not the final world-class state. Target-native behavior contracts | Install Simulation | `scripts/simulate_install.py`, `reports/install_simulation.md`, `tests/verify_install_simulation.py` with installer permission coverage checks | v0 landed | | Local Install Sync Preflight | `scripts/sync_local_install.py`, `tests/verify_local_install_sync.py`, `Makefile` package-check prerequisites | v0 landed | | Upgrade Check | `scripts/upgrade_check.py`, `reports/upgrade_check.md`, `tests/verify_upgrade_check.py` | v0 landed | -| Telemetry & Drift | `scripts/render_adoption_drift_report.py`, `scripts/yao_cli_telemetry.py`, `scripts/emit_telemetry_event.py`, `scripts/render_telemetry_hook_recipes.py`, `scripts/import_telemetry_events.py`, `reports/adoption_drift_report.md`, `reports/telemetry_hook_recipes.md`, `tests/verify_adoption_drift.py`, `tests/verify_telemetry_emit.py`, `tests/verify_telemetry_hooks.py`, `tests/verify_telemetry_import.py`, `tests/verify_yao_cli.py`, `references/telemetry-drift-method.md` | v0 landed | +| Telemetry & Drift | `scripts/render_adoption_drift_report.py`, `scripts/yao_cli_telemetry.py`, `scripts/emit_telemetry_event.py`, `scripts/render_telemetry_hook_recipes.py`, `scripts/telemetry_native_host.py`, `scripts/import_telemetry_events.py`, `reports/adoption_drift_report.md`, `reports/telemetry_hook_recipes.md`, `tests/verify_adoption_drift.py`, `tests/verify_telemetry_emit.py`, `tests/verify_telemetry_hooks.py`, `tests/verify_telemetry_native_host.py`, `tests/verify_telemetry_import.py`, `tests/verify_yao_cli.py`, `references/telemetry-drift-method.md` | v0 landed | | Review Waivers | `scripts/render_review_waivers.py`, `reports/review_waivers.md`, `tests/verify_review_waivers.py`, `references/review-waiver-method.md` | v0 landed | | Governed Permission Gates | `security/permission_policy.json`, `scripts/trust_check.py`, `scripts/render_review_studio.py`, `tests/verify_trust_check.py`, `tests/verify_review_studio.py` | v0 landed | | Runtime Permission Probes | `scripts/probe_runtime_permissions.py`, `reports/runtime_permission_probes.md`, `tests/verify_runtime_permission_probes.py`, `tests/verify_review_studio.py` | v0 landed | @@ -88,9 +89,9 @@ Next move: add richer source-line anchors inside generated reports and record re ### 4. Multi-skill operation now links Atlas with drift, but needs platform-native capture -The new Skill Atlas can scan a workspace and report catalog, route overlap, dependency graph, stale skill, missing owner/review metadata, aggregate drift signals, and no-route opportunities. It now also supports `skill_atlas/policy.json` so release gates distinguish actionable library skills from examples and fixtures while keeping full visibility. Adoption Drift v0 can record metadata-only local events, block raw prompt/output fields, summarize missed-trigger, bad-output, script-error, and review-overdue signals, feed next iteration candidates into Review Studio, and publish aggregate drift input for Atlas. `yao.py` now adds opt-in automatic CLI run capture through `YAO_CLI_TELEMETRY=1` or `--record-cli-telemetry`, recording only `source=yao_cli`, normalized subcommand name, outcome, failure class, and timestamp. `telemetry-emit` gives Browser/Chrome/IDE/wrapper integrations a stable local hook for appending one normalized external event into `.yao/telemetry_spool/external_events.jsonl`, with dry-run validation and no raw content fields. `telemetry-hooks` renders Browser, Chrome, VS Code, CLI wrapper, and provider-adapter recipes with dry-run commands, import commands, trigger points, and explicit `native_auto_capture=false` caveats. `telemetry-import` accepts already-sanitized external client JSONL or the emitted spool, validates the whole file before appending, supports dry-run, defaults `source=external`, and rejects any raw content or unknown metadata fields without mutating the local event stream. It still needs platform-native implementations that call the emit hook automatically from real clients. +The new Skill Atlas can scan a workspace and report catalog, route overlap, dependency graph, stale skill, missing owner/review metadata, aggregate drift signals, and no-route opportunities. It now also supports `skill_atlas/policy.json` so release gates distinguish actionable library skills from examples and fixtures while keeping full visibility. Adoption Drift v0 can record metadata-only local events, block raw prompt/output fields, summarize missed-trigger, bad-output, script-error, and review-overdue signals, feed next iteration candidates into Review Studio, and publish aggregate drift input for Atlas. `yao.py` now adds opt-in automatic CLI run capture through `YAO_CLI_TELEMETRY=1` or `--record-cli-telemetry`, recording only `source=yao_cli`, normalized subcommand name, outcome, failure class, and timestamp. `telemetry-emit` gives Browser/Chrome/IDE/wrapper integrations a stable local hook for appending one normalized external event into `.yao/telemetry_spool/external_events.jsonl`, with dry-run validation and no raw content fields. `telemetry-hooks` renders Browser, Chrome, VS Code, CLI wrapper, and provider-adapter recipes with dry-run commands, import commands, trigger points, and explicit `native_auto_capture=false` caveats. `telemetry_native_host.py` now provides a tested Browser/Chrome Native Messaging host: it reads length-prefixed stdio JSON, rejects raw content fields, writes metadata-only events, and generates an operator-installable launcher plus Chrome host manifest. `telemetry-import` accepts already-sanitized external client JSONL or the emitted spool, validates the whole file before appending, supports dry-run, defaults `source=external`, and rejects any raw content or unknown metadata fields without mutating the local event stream. It still needs an installed real extension or provider client that sends production events to the native host. -Next move: replace the recipes with real Browser, Chrome, IDE, and provider-native implementations that call the emit hook automatically, then let Atlas rank stale, drifting, or conflicting skills by real usage impact. +Next move: install a real Browser/Chrome extension or provider client against the native host and record production metadata events, then let Atlas rank stale, drifting, or conflicting skills by real usage impact. ### 5. Trust report is structural, not full security review @@ -105,22 +106,22 @@ Next move: add real client or installer permission enforcement integration. | Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden | | Runtime Conformance | `5 / 5` targets passing | | Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts | -| Trust | `0` secret findings, `1` pinned dependency file, `10` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `63 / 63` CLI help smoke checks passing across `73` scripts, source-contract hash scope explicit | +| Trust | `0` secret findings, `1` pinned dependency file, `10` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `64 / 64` CLI help smoke checks passing across `74` scripts, source-contract hash scope explicit | | Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired | | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | | Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix | -| Package Verification | `4 / 4` target adapters present, archive verified, `503` zip entries, `0` failures, `0` warnings | -| Install Simulation | archive with `503` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | +| Package Verification | `4 / 4` target adapters present, archive verified, `505` zip entries, `0` failures, `0` warnings | +| Install Simulation | archive with `505` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | -| Adoption Drift | `1` metadata-only review event, `0` adoption samples, adoption `0`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | +| Adoption Drift | `1` metadata-only review event, `0` adoption samples, adoption `0`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | | Review Waivers | ledger generated; current release has `1` warning gate that still needs reviewer decision or a time-bounded waiver; blockers remain non-waivable in v0 | | Review Annotations | ledger generated; current release has `0` reviewer annotations and `0` open annotation blockers | | Review Studio | decision `review`, world-class score `92`, `13` gates, `0` blockers, `2` warnings, `2` review actions, `0` open annotation blockers | | IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable | | Context Budget | initial load `944/1000`, under the production budget | -| CI | `make ci-test` target count is `59` after the telemetry hook recipe gate update | +| CI | `make ci-test` target count is `60` after the telemetry native host gate update | ## Next Highest-Leverage Moves @@ -128,4 +129,4 @@ Next move: add real client or installer permission enforcement integration. 2. Add native client or installer runtime enforcement for approved high-permission capabilities. 3. Run the new provider-backed output runner against holdout cases with real credentials, then record the current blind A/B decisions before claiming fully ready status. 4. Add real reviewer annotation records during the next human review pass. -5. Replace `telemetry-hooks` recipes with platform-native clients that call `telemetry-emit` automatically. +5. Install a real Browser/Chrome extension or provider client against `telemetry_native_host.py` and record production metadata events. diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 78433274..b85efc6b 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -609,7 +609,7 @@
-
完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
上下文成本42入口约 350 个词/字，references 约 15206 个词/字。入口约 350 个词/字，references 约 15206 个词/字。
+
完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
上下文成本42入口约 350 个词/字，references 约 15316 个词/字。入口约 350 个词/字，references 约 15316 个词/字。
@@ -641,10 +641,10 @@

指标判读Reading

先看雷达图判断能力短板，再看下方每项分数的证据原因。分数不是装饰数字，必须和本地文件、reports 证据或证据不足提示对应。Read the radar first for weak spots, then inspect each score with its evidence. Scores must map to local files, reports, or explicit evidence gaps.

-
  1. 稳定Stable完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  2. 稳定Stable触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  3. 稳定Stable证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  4. 稳定Stable可维护性100SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  5. 稳定Stable可迁移性100agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  6. 关注Watch上下文成本42入口约 350 个词/字，references 约 15206 个词/字。入口约 350 个词/字，references 约 15206 个词/字。
+
  1. 稳定Stable完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  2. 稳定Stable触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  3. 稳定Stable证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  4. 稳定Stable可维护性100SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  5. 稳定Stable可迁移性100agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  6. 关注Watch上下文成本42入口约 350 个词/字，references 约 15316 个词/字。入口约 350 个词/字，references 约 15316 个词/字。
-
完整度100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  • README.md 已存在，便于人工阅读。README.md 已存在，便于人工阅读。
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml 已存在，便于跨平台适配。
触发清晰100
  • frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  • description 有足够长度说明任务边界。description 有足够长度说明任务边界。
  • description 已包含使用场景或排除边界信号。description 已包含使用场景或排除边界信号。
证据充分100
  • 已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  • skill-ir.json 已存在。skill-ir.json 已存在。
  • compiled_targets.json 已存在。compiled_targets.json 已存在。
可维护性100
  • SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  • 入口文件保持克制，可维护性较好。入口文件保持克制，可维护性较好。
  • references/ 已承载扩展指导。references/ 已承载扩展指导。
可迁移性100
  • agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  • manifest.json 已存在。manifest.json 已存在。
  • 目标平台或 adapter target 已声明。目标平台或 adapter target 已声明。
上下文成本42
  • 入口约 350 个词/字，references 约 15206 个词/字。入口约 350 个词/字，references 约 15206 个词/字。
  • 分数越高代表上下文成本越低。分数越高代表上下文成本越低。
  • 上下文成本偏高，建议压缩入口或拆分 references。上下文成本偏高，建议压缩入口或拆分 references。
+
完整度100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  • README.md 已存在，便于人工阅读。README.md 已存在，便于人工阅读。
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml 已存在，便于跨平台适配。
触发清晰100
  • frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  • description 有足够长度说明任务边界。description 有足够长度说明任务边界。
  • description 已包含使用场景或排除边界信号。description 已包含使用场景或排除边界信号。
证据充分100
  • 已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  • skill-ir.json 已存在。skill-ir.json 已存在。
  • compiled_targets.json 已存在。compiled_targets.json 已存在。
可维护性100
  • SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  • 入口文件保持克制，可维护性较好。入口文件保持克制，可维护性较好。
  • references/ 已承载扩展指导。references/ 已承载扩展指导。
可迁移性100
  • agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  • manifest.json 已存在。manifest.json 已存在。
  • 目标平台或 adapter target 已声明。目标平台或 adapter target 已声明。
上下文成本42
  • 入口约 350 个词/字，references 约 15316 个词/字。入口约 350 个词/字，references 约 15316 个词/字。
  • 分数越高代表上下文成本越低。分数越高代表上下文成本越低。
  • 上下文成本偏高，建议压缩入口或拆分 references。上下文成本偏高，建议压缩入口或拆分 references。
@@ -720,7 +720,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。已生成 Skill IR，核心语义可先于平台打包被审查和迁移。保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。保留并复用Keep
缺口Gap上下文成本需要补强：入口约 350 个词/字，references 约 15206 个词/字。上下文成本需要补强：入口约 350 个词/字，references 约 15206 个词/字。纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。已生成 Skill IR，核心语义可先于平台打包被审查和迁移。保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。保留并复用Keep
缺口Gap上下文成本需要补强：入口约 350 个词/字，references 约 15316 个词/字。上下文成本需要补强：入口约 350 个词/字，references 约 15316 个词/字。纳入下一轮修复Fix next
@@ -771,7 +771,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布310项SKILL.mdREADME.mdagents/interface.yamlmanifest.jsonreferencesscripts
资产分布图展示当前包体的文件和目录重心。
+
资产分布311项SKILL.mdREADME.mdagents/interface.yamlmanifest.jsonreferencesscripts
资产分布图展示当前包体的文件和目录重心。
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index da970a66..2f631b40 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -96,7 +96,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 350 个词/字，references 约 15206 个词/字。", + "入口约 350 个词/字，references 约 15316 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -200,7 +200,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 350 个词/字，references 约 15206 个词/字。" + "上下文成本需要补强：入口约 350 个词/字，references 约 15316 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -433,7 +433,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 73 + "file_count": 74 }, { "path": "evals", @@ -448,7 +448,7 @@ "file_count": 173 } ], - "file_count": 310, + "file_count": 311, "folder_count": 4, "distribution": [ { @@ -473,7 +473,7 @@ }, { "label": "scripts", - "value": 73 + "value": 74 }, { "label": "evals", @@ -602,7 +602,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 73 + "file_count": 74 }, { "path": "evals", @@ -948,8 +948,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 157, - "script_count": 73, + "scanned_files": 158, + "script_count": 74, "internal_module_count": 10, "secret_findings": 0, "dependency_files": [ @@ -958,18 +958,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 50, + "file_write_script_count": 51, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 63, + "help_smoke_checked_count": 64, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 157, - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "package_hash_file_count": 158, + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" }, "skill_atlas": { "skill_count": 12, @@ -1007,8 +1007,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339", - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "package_sha256": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, "compatibility": { "openai": "pass", @@ -1039,7 +1039,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1055,8 +1055,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf", - "archive_entry_count": 503, + "archive_sha256": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3", + "archive_entry_count": 505, "failure_count": 0, "warning_count": 0 }, @@ -1067,7 +1067,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 503, + "archive_entry_count": 505, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1134,12 +1134,12 @@ { "field": "archive_sha256", "from": "", - "to": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "to": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "to": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index 124f9e33..4c94294e 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -128,6 +128,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 865512e7..2f5fbce6 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "15aac04026bdedbd4c4e4a8eb9ac2cd95b2cda1ffe9735cdb706b0f4393aceaf" + "to": "7494bf9b978d58b663cc0e8b6ffe2531a84602385f6f517774320197d30170d3" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "25df24e0cb24e09a1a11819ca6c185b60c279a4f12851ef1ce9275e67a58d339" + "to": "e42a9c4cf0f22cd6fc047dff3da1a380f5cc9e17157a48d8a1ac2071f7c84fbc" } ] }, diff --git a/scripts/ci_test.py b/scripts/ci_test.py index dfb71cc5..8f88a045 100644 --- a/scripts/ci_test.py +++ b/scripts/ci_test.py @@ -53,6 +53,7 @@ DEFAULT_TARGETS = [ "telemetry-import-check", "telemetry-emit-check", "telemetry-hooks-check", + "telemetry-native-host-check", "review-waivers-check", "review-annotations-check", "baseline-compare-check", diff --git a/scripts/telemetry_native_host.py b/scripts/telemetry_native_host.py new file mode 100644 index 00000000..f3520559 --- /dev/null +++ b/scripts/telemetry_native_host.py @@ -0,0 +1,229 @@ +#!/usr/bin/env python3 +import argparse +import json +import os +import shlex +import stat +import struct +import sys +from pathlib import Path +from typing import Any, BinaryIO + +from emit_telemetry_event import append_event, default_spool_path +from render_adoption_drift_report import display_path, normalize_event, skill_defaults + + +SCHEMA_VERSION = "1.0" +DEFAULT_HOST_NAME = "com.yao.meta_skill.telemetry" +DEFAULT_DESCRIPTION = "Yao metadata-only telemetry native messaging host" +SKILL_DIR_ENV = "YAO_TELEMETRY_SKILL_DIR" +EVENTS_ENV = "YAO_TELEMETRY_EVENTS" +MAX_MESSAGE_BYTES = 1024 * 1024 + + +def read_native_message(stream: BinaryIO) -> dict[str, Any] | None: + header = stream.read(4) + if not header: + return None + if len(header) != 4: + raise ValueError("native message header must be exactly 4 bytes") + size = struct.unpack(" MAX_MESSAGE_BYTES: + raise ValueError(f"native message is too large: {size} bytes") + payload = stream.read(size) + if len(payload) != size: + raise ValueError("native message payload ended before declared length") + message = json.loads(payload.decode("utf-8")) + if not isinstance(message, dict): + raise ValueError("native message must be a JSON object") + return message + + +def write_native_message(stream: BinaryIO, payload: dict[str, Any]) -> None: + data = json.dumps(payload, ensure_ascii=False, sort_keys=True).encode("utf-8") + stream.write(struct.pack(" dict[str, Any]: + raw = dict(raw_message) + raw.setdefault("source", "external") + raw.setdefault("command", "native-messaging-host") + event, failures = normalize_event(raw, skill_defaults(skill_dir), "native-host-message") + if event and not failures and not dry_run: + append_event(output_jsonl, event) + return { + "ok": not failures, + "schema_version": SCHEMA_VERSION, + "mode": "native-messaging-host", + "skill_dir": display_path(skill_dir), + "output_jsonl": display_path(output_jsonl), + "dry_run": dry_run, + "emitted": bool(event and not failures and not dry_run), + "event": event or {}, + "failures": failures, + } + + +def write_launcher(path: Path, host_script: Path, skill_dir: Path, output_jsonl: Path) -> None: + path.parent.mkdir(parents=True, exist_ok=True) + script = "\n".join( + [ + "#!/bin/sh", + "set -eu", + ( + "exec python3 " + f"{shlex.quote(str(host_script.resolve()))} " + f"{shlex.quote(str(skill_dir.resolve()))} " + "--stdio " + f"--output-jsonl {shlex.quote(str(output_jsonl.resolve()))}" + ), + "", + ] + ) + path.write_text(script, encoding="utf-8") + current = path.stat().st_mode + path.chmod(current | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH) + + +def write_manifest( + manifest_path: Path, + host_name: str, + description: str, + host_path: Path, + allowed_origins: list[str], +) -> dict[str, Any]: + failures: list[str] = [] + if not allowed_origins: + failures.append("At least one --allowed-origin is required for a Chrome native messaging manifest.") + for origin in allowed_origins: + if not origin.startswith("chrome-extension://") or not origin.endswith("/"): + failures.append(f"Unsupported Chrome extension origin: {origin}") + if not host_path.exists(): + failures.append(f"Native host path does not exist: {host_path}") + elif not os.access(host_path, os.X_OK): + failures.append(f"Native host path must be executable: {host_path}") + manifest = { + "name": host_name, + "description": description, + "path": str(host_path.resolve()), + "type": "stdio", + "allowed_origins": allowed_origins, + } + if not failures: + manifest_path.parent.mkdir(parents=True, exist_ok=True) + manifest_path.write_text(json.dumps(manifest, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") + return { + "ok": not failures, + "schema_version": SCHEMA_VERSION, + "manifest": manifest, + "manifest_path": display_path(manifest_path), + "failures": failures, + } + + +def run_stdio(skill_dir: Path, output_jsonl: Path, dry_run: bool) -> int: + while True: + raw = read_native_message(sys.stdin.buffer) + if raw is None: + return 0 + response = emit_native_message(skill_dir, output_jsonl, raw, dry_run=dry_run) + write_native_message(sys.stdout.buffer, response) + + +def env_default(name: str, fallback: str) -> str: + return os.environ.get(name) or fallback + + +def main() -> None: + parser = argparse.ArgumentParser(description="Run a metadata-only telemetry native messaging host.") + parser.add_argument("skill_dir", nargs="?", default=env_default(SKILL_DIR_ENV, ".")) + parser.add_argument("--output-jsonl", default=os.environ.get(EVENTS_ENV)) + parser.add_argument("--message-json", help="Emit one JSON object directly, useful for host smoke tests.") + parser.add_argument("--stdio", action="store_true", help="Use Chrome/Browser Native Messaging length-prefixed stdio.") + parser.add_argument("--dry-run", action="store_true") + parser.add_argument("--write-manifest") + parser.add_argument("--write-launcher") + parser.add_argument("--host-name", default=DEFAULT_HOST_NAME) + parser.add_argument("--description", default=DEFAULT_DESCRIPTION) + parser.add_argument("--allowed-origin", action="append", default=[]) + parser.add_argument("--host-path") + args = parser.parse_args() + + skill_dir = Path(args.skill_dir).resolve() + output_jsonl = Path(args.output_jsonl).resolve() if args.output_jsonl else default_spool_path(skill_dir).resolve() + host_script = Path(__file__).resolve() + + launcher_path = Path(args.write_launcher).resolve() if args.write_launcher else None + if launcher_path: + write_launcher(launcher_path, host_script, skill_dir, output_jsonl) + + if args.write_manifest: + host_path = Path(args.host_path).resolve() if args.host_path else launcher_path or host_script + report = write_manifest( + Path(args.write_manifest).resolve(), + args.host_name, + args.description, + host_path, + args.allowed_origin, + ) + if launcher_path: + report["launcher_path"] = display_path(launcher_path) + print(json.dumps(report, ensure_ascii=False, indent=2)) + if not report["ok"]: + raise SystemExit(2) + return + + if args.stdio: + try: + raise SystemExit(run_stdio(skill_dir, output_jsonl, args.dry_run)) + except Exception as exc: + write_native_message( + sys.stdout.buffer, + { + "ok": False, + "schema_version": SCHEMA_VERSION, + "mode": "native-messaging-host", + "emitted": False, + "failures": [str(exc)], + }, + ) + raise SystemExit(2) + + if args.message_json: + try: + message = json.loads(args.message_json) + except json.JSONDecodeError as exc: + print(json.dumps({"ok": False, "failures": [f"Invalid --message-json: {exc.msg}"]}, ensure_ascii=False, indent=2)) + raise SystemExit(2) + if not isinstance(message, dict): + print(json.dumps({"ok": False, "failures": ["--message-json must decode to a JSON object"]}, ensure_ascii=False, indent=2)) + raise SystemExit(2) + report = emit_native_message(skill_dir, output_jsonl, message, dry_run=args.dry_run) + print(json.dumps(report, ensure_ascii=False, indent=2)) + if not report["ok"]: + raise SystemExit(2) + return + + print( + json.dumps( + { + "ok": False, + "schema_version": SCHEMA_VERSION, + "failures": ["Use --message-json, --stdio, or --write-manifest."], + }, + ensure_ascii=False, + indent=2, + ) + ) + raise SystemExit(2) + + +if __name__ == "__main__": + main() diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index e43677d1..9b8da773 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -172,6 +172,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 5e870dc6..e031f2e4 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -84,6 +84,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/sync_local_install.py", + "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", "scripts/upgrade_check.py", diff --git a/tests/verify_telemetry_native_host.py b/tests/verify_telemetry_native_host.py new file mode 100644 index 00000000..b1443e1a --- /dev/null +++ b/tests/verify_telemetry_native_host.py @@ -0,0 +1,218 @@ +#!/usr/bin/env python3 +import json +import shutil +import struct +import subprocess +import sys +from pathlib import Path + + +ROOT = Path(__file__).resolve().parent.parent +TMP = ROOT / "tests" / "tmp_telemetry_native_host" +HOST = ROOT / "scripts" / "telemetry_native_host.py" +YAO = ROOT / "scripts" / "yao.py" +ORIGIN = "chrome-extension://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/" + + +def run(cmd: list[str]) -> dict: + proc = subprocess.run(cmd, cwd=ROOT, capture_output=True, text=True) + payload = json.loads(proc.stdout) if proc.stdout.strip() else {} + return { + "ok": proc.returncode == 0, + "returncode": proc.returncode, + "payload": payload, + "stdout": proc.stdout, + "stderr": proc.stderr, + } + + +def pack_message(payload: dict) -> bytes: + data = json.dumps(payload, ensure_ascii=False).encode("utf-8") + return struct.pack(" list[dict]: + messages = [] + offset = 0 + while offset < len(data): + size = struct.unpack(" list[dict]: + if not path.exists(): + return [] + return [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines() if line.strip()] + + +def main() -> None: + shutil.rmtree(TMP, ignore_errors=True) + TMP.mkdir(parents=True, exist_ok=True) + subprocess.run( + [ + sys.executable, + str(ROOT / "scripts" / "init_skill.py"), + "telemetry-native-host-demo", + "--description", + "Receive metadata-only telemetry events from a Browser native messaging host.", + "--output-dir", + str(TMP), + ], + cwd=ROOT, + check=True, + capture_output=True, + text=True, + ) + skill_dir = TMP / "telemetry-native-host-demo" + spool = TMP / "native-spool.jsonl" + + valid = run( + [ + sys.executable, + str(HOST), + str(skill_dir), + "--output-jsonl", + str(spool), + "--message-json", + json.dumps( + { + "event": "skill_activation", + "activation_type": "explicit", + "outcome": "accepted", + "failure_type": "none", + "command": "chrome-native-host", + } + ), + ] + ) + assert valid["ok"], valid + assert valid["payload"]["emitted"] is True, valid + events = read_jsonl(spool) + assert len(events) == 1, events + assert events[0]["command"] == "chrome-native-host", events + assert events[0]["source"] == "external", events + + invalid = run( + [ + sys.executable, + str(HOST), + str(skill_dir), + "--output-jsonl", + str(spool), + "--message-json", + json.dumps( + { + "event": "skill_activation", + "activation_type": "explicit", + "outcome": "accepted", + "failure_type": "none", + "command": "chrome-native-host", + "prompt": "raw prompt must not pass through native host", + } + ), + ] + ) + assert invalid["returncode"] == 2, invalid + assert "raw content fields" in "\n".join(invalid["payload"]["failures"]), invalid + assert len(read_jsonl(spool)) == 1, read_jsonl(spool) + + stdio_payload = pack_message( + { + "event": "skill_output", + "activation_type": "manual", + "outcome": "edited", + "failure_type": "none", + "command": "browser-native-host", + } + ) + stdio = subprocess.run( + [ + sys.executable, + str(HOST), + str(skill_dir), + "--output-jsonl", + str(spool), + "--stdio", + ], + cwd=ROOT, + input=stdio_payload, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + ) + assert stdio.returncode == 0, stdio.stderr + responses = unpack_messages(stdio.stdout) + assert len(responses) == 1, responses + assert responses[0]["ok"], responses + assert responses[0]["emitted"] is True, responses + assert len(read_jsonl(spool)) == 2, read_jsonl(spool) + + manifest = TMP / "native-host-manifest.json" + launcher = TMP / "yao-telemetry-native-host.sh" + manifest_result = run( + [ + sys.executable, + str(HOST), + str(skill_dir), + "--output-jsonl", + str(spool), + "--write-launcher", + str(launcher), + "--write-manifest", + str(manifest), + "--allowed-origin", + ORIGIN, + ] + ) + assert manifest_result["ok"], manifest_result + assert manifest.exists(), manifest + assert launcher.exists(), launcher + assert launcher.stat().st_mode & 0o111, launcher.stat().st_mode + manifest_payload = json.loads(manifest.read_text(encoding="utf-8")) + assert manifest_payload["name"] == "com.yao.meta_skill.telemetry", manifest_payload + assert manifest_payload["type"] == "stdio", manifest_payload + assert manifest_payload["path"] == str(launcher.resolve()), manifest_payload + assert manifest_payload["allowed_origins"] == [ORIGIN], manifest_payload + + manifest_without_launcher = TMP / "native-host-manifest-without-launcher.json" + manifest_without_launcher_result = run( + [ + sys.executable, + str(HOST), + str(skill_dir), + "--write-manifest", + str(manifest_without_launcher), + "--allowed-origin", + ORIGIN, + ] + ) + assert manifest_without_launcher_result["returncode"] == 2, manifest_without_launcher_result + assert not manifest_without_launcher.exists(), manifest_without_launcher + assert "must be executable" in "\n".join(manifest_without_launcher_result["payload"]["failures"]) + + imported = run( + [ + sys.executable, + str(YAO), + "telemetry-import", + str(skill_dir), + "--input-jsonl", + str(spool), + "--generated-at", + "2026-06-13T12:30:00Z", + ] + ) + assert imported["ok"], imported + assert imported["payload"]["imported_count"] == 2, imported + assert imported["payload"]["adoption_drift"]["summary"]["source_types"]["external"] == 2, imported + assert imported["payload"]["adoption_drift"]["summary"]["command_counts"]["chrome-native-host"] == 1, imported + assert imported["payload"]["adoption_drift"]["summary"]["command_counts"]["browser-native-host"] == 1, imported + + print(json.dumps({"ok": True}, ensure_ascii=False, indent=2)) + + +if __name__ == "__main__": + main()
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder